Sub-Image Anomaly Detection with Deep Pyramid Correspondences

Abstract

Nearest neighbor (kNN) methods utilizing deep pre-trained features exhibit very strong anomaly detection performance when applied to entire images. A limitation of kNN methods is the lack of segmentation map describing where the anomaly lies inside the image. In this work we present a novel anomaly segmentation approach based on alignment between an anomalous image and a constant number of the similar normal images. Our method, Semantic Pyramid Anomaly Detection (SPADE) uses correspondences based on a multi-resolution feature pyramid. SPADE is shown to achieve state-of-the-art performance on unsupervised anomaly detection and localization while requiring virtually no training time.

References in corpus (10)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Language Models are Few-Shot Learners
• Self-Attention Generative Adversarial Networks
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Deep Anomaly Detection with Outlier Exposure
• Deep Anomaly Detection Using Geometric Transformations
• Deep Nearest Neighbor Anomaly Detection
• Classification-Based Anomaly Detection for General Data
• Attribute Restoration Framework for Anomaly Detection
• Differentiable Pooling for Hierarchical Feature Learning

Cited by in corpus (25)

• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
• FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
• Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Student-Teacher Feature Pyramid Matching for Anomaly Detection
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
• REB: Reducing Biases in Representation for Industrial Anomaly Detection
• Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation
• Unsupervised Pathology Detection: A Deep Dive Into the State of the Art
• PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching
• Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
• Visual Anomaly Detection for Images: A Survey
• Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching
• AnomalyHop: An SSL-based Image Anomaly Localization Method
• Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization
• GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
• Anomaly Detection via Self-organizing Map
• Energy-Based Anomaly Detection and Localization
• Learning to Be a Transformer to Pinpoint Anomalies
• Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection
• ATAC-Net: Zoomed view works better for Anomaly Detection
• Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection